<ul><li>NVIDIA has launched Garak, an open-source vulnerability scanner designed to identify potential weaknesses in LLMs.</li><li>Garak acts as a red-teaming and assessment tool for generative AI systems.</li><li>It evaluates LLMs for vulnerabilities such as hallucinations, data leaks, prompt injections, misinformation, toxicity, and jailbreak scenarios.</li><li>Garak supports Hugging Face Hub generative models, replicate text models, and OpenAI API chat and continuation models.</li></ul>

NVIDIA Releases Garak to Safeguard LLMs

Discover more